Title
Wavelet Kernel Penalized Estimation For Non-Equispaced Design Regression
Keywords
Besov spaces; Entropy; Penalization; Reproducing kernel; Smoothing splines ANOVA; Wavelet decomposition
Abstract
The paper considers regression problems with univariate design points. The design points are irregular and no assumptions on their distribution are imposed. The regression function is retrieved by a wavelet based reproducing kernel Hilbert space (RKHS) technique with the penalty equal to the sum of blockwise RKHS norms. In order to simplify numerical optimization, the problem is replaced by an equivalent quadratic minimization problem with an additional penalty term. The computational algorithm is described in detail and is implemented with both the sets of simulated and real data. Comparison with existing methods showed that the technique suggested in the paper does not oversmooth the function and is superior in terms of the mean squared error. It is also demonstrated that under additional assumptions on design points the method achieves asymptotic optimality in a wide range of Besov spaces. © Springer Science + Business Media, Inc. 2006.
Publication Date
3-1-2006
Publication Title
Statistics and Computing
Volume
16
Issue
1
Number of Pages
37-55
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1007/s11222-006-5283-4
Copyright Status
Unknown
Socpus ID
33644555212 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/33644555212
STARS Citation
Amato, Umberto; Antoniadis, Anestis; and Pensky, Marianna, "Wavelet Kernel Penalized Estimation For Non-Equispaced Design Regression" (2006). Scopus Export 2000s. 8519.
https://stars.library.ucf.edu/scopus2000/8519